Related papers: Learning World Graphs to Accelerate Hierarchical R…

Hierarchical Reinforcement Learning (HRL) has made notable progress in complex control tasks by leveraging temporal abstraction. However, previous HRL algorithms often suffer from serious data inefficiency as environments get large. The…

Reinforcement learning (RL) plays a major role in solving complex sequential decision-making tasks. Hierarchical and goal-conditioned RL are promising methods for dealing with two major problems in RL, namely sample inefficiency and…

One of the central challenges faced by a reinforcement learning (RL) agent is to effectively learn a (near-)optimal policy in environments with large state spaces having sparse and noisy feedback signals. In real-world applications, an…

When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…

How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set…

This work presents a Hierarchical Multi-Agent Reinforcement Learning framework for analyzing simulated air combat scenarios involving heterogeneous agents. The objective is to identify effective Courses of Action that lead to mission…

General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large collections of distinct skills, but mutual information is…

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments,…

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…

Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for…

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation…

A heterogeneous graph consists of different vertices and edges types. Learning on heterogeneous graphs typically employs meta-paths to deal with the heterogeneity by reducing the graph to a homogeneous network, guide random walks or capture…

Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning. However, automatically finding potential functions for complex environments is a difficult problem (in fact,…

Social learning algorithms provide models for the formation of opinions over social networks resulting from local reasoning and peer-to-peer exchanges. Interactions occur over an underlying graph topology, which describes the flow of…

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

In recent years, there has been some outstanding work on applying deep reinforcement learning to multi-agent settings. Often in such multi-agent scenarios, adversaries can be present. We address the requirements of such a setting by…

Despite advances in hierarchical reinforcement learning, its applications to path planning in autonomous driving on highways are challenging. One reason is that conventional hierarchical reinforcement learning approaches are not amenable to…

We provide a framework for exploring physics beyond the Standard Model with reinforcement learning using graph representations of new physics theories. The graph structure allows for model-building without a priori specifying definite…